ClawHub
Back to skill

Security audit

Multi-Platform Social Media Scheduler

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only social media scheduling skill whose account and analytics risks are expected for its stated purpose, with no hidden code or install-time behavior found.

Before using this with real social accounts, use platform-approved OAuth or delegated access with minimal scopes, avoid pasting secrets into chat, confirm every account/platform/content/time before scheduling or publishing, and treat exported audience or analytics data as sensitive business data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs users to connect multiple social media and business accounts and aggregate analytics, but it does not disclose the scope of account access, what data will be transmitted or stored, or the privacy and security implications of linking those accounts. In a multi-platform scheduler context, this can expose tokens, posting authority, audience data, and business analytics to unintended collection or misuse, especially if users are prompted to connect high-value brand accounts without informed consent or least-privilege guidance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.